Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/13758 > This PR also optimize generate code of projection for an primitive type array. While we know primitive type array does not require null check and has contiguous data region, this PR performs bulk data copy by using Platform.copy without null checks. if the input array is primitive array, it should in unsafe format and we will just copy the binary, so what's the use case for this optimization? Besides, proving a faster `GenericArrayData` is not an optimization for me, if we don't get an end-to-end performance boost.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org